{"cells":[{"metadata":{},"cell_type":"markdown","source":"This notebook basically ensembles previous submission by these two great kernels. [Inference Single Model Melanoma Starter](https://www.kaggle.com/shonenkov/inference-single-model-melanoma-starter/) by [Alex Shonenkov](https://www.kaggle.com/shonenkov) and [Image And Tabular Data - 0.915](https://www.kaggle.com/cdeotte/image-and-tabular-data-0-915) by [Chris Deotte](https://www.kaggle.com/cdeotte). Please upvote their original work. \n\n---\n* The first kernel [Inference Single Model Melanoma Starter](https://www.kaggle.com/shonenkov/inference-single-model-melanoma-starter/) produces inference from the follwoing three datasets. \n    - [Melanoma Detection Dataset](https://www.kaggle.com/wanderdust/skin-lesion-analysis-toward-melanoma-detection)\n    - [Skin Lesion Images for Melanoma Classification](https://www.kaggle.com/andrewmvd/isic-2019)\n    - [Skin Cancer MNIST: HAM10000](https://www.kaggle.com/kmader/skin-cancer-mnist-ham10000)\n    - [SIIM-ISIC Melanoma Classification](https://www.kaggle.com/c/siim-isic-melanoma-classification/data)\n---\n\nThe second kernel [Image And Tabular Data - 0.915](https://www.kaggle.com/cdeotte/image-and-tabular-data-0-915) by [Chris Deotte] combines both image dataset and metadata given in the CSV files from  [SIIM-ISIC Melanoma Classification](https://www.kaggle.com/c/siim-isic-melanoma-classification/data) dataset. \n\nIf someone converts the four combined dataset into **`TFRecord`** format, it will be awesome to train them on TPUs. I managed to get** public LB score of 93.2 ** with this ensemble by just 3 submission. Hope to explore them further. \n\nPlease upvote if you like this.\n\nThank you.. ","execution_count":null},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd ","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"sub_image = pd.read_csv('/kaggle/input/melanoma-submissions2/submissionImage.csv')\nsub_tabular_70 = pd.read_csv('/kaggle/input/melanoma-submissions2/submissionTabular.csv')\nsub_multiple = pd.read_csv('/kaggle/input/melanoma-submissions2/submission_multiple_data_source.csv')\nsub_public_merge = pd.read_csv('/kaggle/input/submission-9/submission_935.csv')\nsub = pd.read_csv('/kaggle/input/siim-isic-melanoma-classification/sample_submission.csv')\nsub_tabular_78 = pd.read_csv('/kaggle/input/tabular-prediction/submission_tabular_78.csv')\nsub_mean = pd.read_csv('/kaggle/input/siim-isic-multiple-model-training-stacking-923/submission_mean.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# sub.target = sub_multiple.target *0.0 + sub_mean.target *0.55 + sub_tabular.target *0.45\n\n\n## This line got me the public score of 94.0\n# sub.target = sub_mean.target *0.2 + sub_public_merge.target *0.6 + sub_tabular_70.target *0.2 \n\n\n\nsub.target = sub_mean.target *0.29 + sub_public_merge.target *0.69 + sub_tabular_78.target *0.02","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub.to_csv('submission.csv', index = False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}